Cover Image

The AI off-switch problem as a signalling game: bounded rationality and incomparability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Benavoli, Alessio, Facchini, Alessandro, Zaffalon, Marco
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Why AI Safety Requires Uncertainty, Incomplete Preferences, and Non-Archimedean Utilities
by: Benavoli, Alessio, et al.
Published: (2025)

Connecting classical finite exchangeability to quantum theory
by: Benavoli, Alessio, et al.
Published: (2023)

dynoGP: Deep Gaussian Processes for dynamic system identification
by: Benavoli, Alessio, et al.
Published: (2025)

A tutorial on learning from preferences and choices with Gaussian Processes
by: Benavoli, Alessio, et al.
Published: (2024)

Constraint- and Score-Based Nonlinear Granger Causality Discovery with Kernels
by: Murphy, Fiona, et al.
Published: (2026)

A Note on Bayesian Networks with Latent Root Variables
by: Zaffalon, Marco, et al.
Published: (2024)

Automatic Causal Fairness Analysis with LLM-Generated Reporting
by: Berarducci, Alessia, et al.
Published: (2026)

COPA: Comparing the incomparable in multi-objective model evaluation
by: Javaloy, Adrián, et al.
Published: (2025)

Epistemology gives a Future to Complementarity in Human-AI Interactions
by: Ferrario, Andrea, et al.
Published: (2026)

Quantum Wiener architecture for quantum reservoir computing
by: Benavoli, Alessio, et al.
Published: (2026)

A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes
by: Benfenati, Alessandro, et al.
Published: (2024)

On the influence of dependent features in classification problems: a game-theoretic perspective
by: Davila-Pena, Laura, et al.
Published: (2024)

Prediction and Causality of functional MRI and synthetic signal using a Zero-Shot Time-Series Foundation Model
by: Crimi, Alessandro, et al.
Published: (2025)

AlphaViT: A flexible game-playing AI for multiple games and variable board sizes
by: Fujita, Kazuhisa
Published: (2024)

Additive decomposition of one-dimensional signals using Transformers
by: Salti, Samuele, et al.
Published: (2025)

A finite-sample bound for identifying partially observed linear switched systems from a single trajectory
by: Racz, Daniel, et al.
Published: (2025)

Causal Discovery on Higher-Order Interactions
by: Zanga, Alessio, et al.
Published: (2025)

Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation
by: Giorlandino, Alessio, et al.
Published: (2025)

Trading off rewards and errors in multi-armed bandits
by: Erraqabi, Akram, et al.
Published: (2026)

Function Based Isolation Forest (FuBIF): A Unifying Framework for Interpretable Isolation-Based Anomaly Detection
by: Arcudi, Alessio, et al.
Published: (2025)

Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
by: Súkeník, Peter, et al.
Published: (2026)

Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts
by: Lotfi, Sanae, et al.
Published: (2026)

Modelling bounded rational decision-making through Wasserstein constraints
by: Evans, Benjamin Patrick, et al.
Published: (2025)

The logic of rational graph neural networks
by: Khalife, Sammy
Published: (2023)

An adaptive approach to Bayesian Optimization with switching costs
by: Pricopie, Stefan, et al.
Published: (2024)

The representation landscape of few-shot learning and fine-tuning in large language models
by: Doimo, Diego, et al.
Published: (2024)

Solving Bayesian inverse problems with diffusion priors and off-policy RL
by: Scimeca, Luca, et al.
Published: (2025)

Approximate information maximization for bandit games
by: Barbier-Chebbah, Alex, et al.
Published: (2023)

An Improved Algorithm for Learning Drifting Discrete Distributions
by: Mazzetto, Alessio
Published: (2024)

Gaussian process policy iteration with additive Schwarz acceleration for forward and inverse HJB and mean field game problems
by: Yang, Xianjin, et al.
Published: (2025)

Unified theory of upper confidence bound policies for bandit problems targeting total reward, maximal reward, and more
by: Kikkawa, Nobuaki, et al.
Published: (2024)

On rankings in multiplayer games with an application to the game of Whist
by: Coyette, Alexis, et al.
Published: (2026)

AI Agents as Universal Task Solvers
by: Achille, Alessandro, et al.
Published: (2025)

Unified continuous-time q-learning for mean-field game and mean-field control problems
by: Wei, Xiaoli, et al.
Published: (2024)

Small transformer architectures for task switching
by: Gros, Claudius
Published: (2025)

Computations and ML for surjective rational maps
by: Karzhemanov, Ilya
Published: (2025)

Planning in entropy-regularized Markov decision processes and games
by: Grill, Jean-Bastien, et al.
Published: (2026)

Tackling the Accuracy-Interpretability Trade-off in a Hierarchy of Machine Learning Models for the Prediction of Extreme Heatwaves
by: Lovo, Alessandro, et al.
Published: (2024)

When to Forget? Complexity Trade-offs in Machine Unlearning
by: Van Waerebeke, Martin, et al.
Published: (2025)

Water Quality Estimation Through Machine Learning Multivariate Analysis
by: Cardia, Marco, et al.
Published: (2025)